Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

A scheme is developed for classifying the types of motion perceived by a humanlike robot. It is assumed that the robot receives visual images of the scene using a perspective system model. Equations, theorems, concepts, clues, etc., relating the objects, their positions, and their motion to their images on the focal plane are presented. >

http://ieeexplore.ieee.org/iel2/815/3148/00100651.pdf

Robot vision

Communications of the ACM (CACM for short, not the best sounding acronym around) is the ACM’s flagship magazine. Started in 1957, CACM is handy for keeping up to date on current research being carried out across all topics of computer science and realworld applications. CACM has had an illustrious past with many influential pieces of work and debates started within its pages. These include Hoare’s presentation of the Quicksort algorithm; Rivest, Shamir and Adleman’s description of the first publickey cryptosystem RSA; and Dijkstra’s famous letter against the use of GOTO. In addition to the print edition, which is released monthly, there is a fantastic website (http://cacm.acm. org/) that showcases not only the most recent edition but all previous CACM articles as well, readable online as well as downloadable as a PDF. In addition, the website lets you browse for articles by subject, a handy feature if you want to focus on a particular topic. CACM is really essential reading. Pretty much guaranteed to contain content that is interesting to anyone, it keeps tabs on the latest in computer science. It is a valuable asset for us students, who tend to delve deep into a particular area of CS and forget everything that is happening around us. — Daniel Gooch U ndergraduate research is like a box of chocolates: You never know what kind of project you will get. That being said, there are still a few things you should know to get the most out of the experience.

Communications of the ACM

Modern digital cameras employ silicon focal plane array (FPA) image sensors featuring millions of pixels. However, it is possible to make a camera that only needs one pixel. In these cameras a spatial light modulator, placed before or after the object to be imaged, applies a time-varying pattern and synchronized intensity measurements are made with a single-pixel detector. The principle of compressed sensing then allows an image to be generated. As the approach suits a wide a variety of detector technologies, images can be collected at wavelengths outside the reach of FPA technology or at high frame rates or in three dimensions. Promising applications include the visualization of hazardous gas leaks and 3D situation awareness for autonomous vehicles. Rather than requiring millions of pixels, it is possible to make a camera that only needs one pixel. This Review details the working principle, advantages, technical considerations and future potential of single-pixel imaging.

Principles and prospects for single-pixel imaging

A three-dimensional imaging system which distributes the optical illumination over the full field-of-view is sought after. Here, the authors demonstrate the capability of reconstructing 128 × 128 pixel resolution three-dimensional scenes to an accuracy of 3 mm as well as real-time video with a frame-rate up to 12 Hz.

Single-pixel three-dimensional imaging with time-based depth resolution

Single-pixel imaging is an alternate imaging technique particularly well-suited to imaging modalities such as hyper-spectral imaging, depth mapping, 3D profiling. However, the single-pixel technique requires sequential measurements resulting in a trade-off between spatial resolution and acquisition time, limiting real-time video applications to relatively low resolutions. Compressed sensing techniques can be used to improve this trade-off. However, in this low resolution regime, conventional compressed sensing techniques have limited impact due to lack of sparsity in the datasets. Here we present an alternative compressed sensing method in which we optimize the measurement order of the Hadamard basis, such that at discretized increments we obtain complete sampling for different spatial resolutions. In addition, this method uses deterministic acquisition, rather than the randomized sampling used in conventional compressed sensing. This so-called ‘Russian Dolls’ ordering also benefits from minimal computational overhead for image reconstruction. We find that this compressive approach performs as well as other compressive sensing techniques with greatly simplified post processing, resulting in significantly faster image reconstruction. Therefore, the proposed method may be useful for single-pixel imaging in the low resolution, high-frame rate regime, or video-rate acquisition.

/pdf/a-russian-dolls-ordering-of-the-hadamard-basis-for-1somfuqiba.pdf

A Russian Dolls ordering of the Hadamard basis for compressive single-pixel imaging.

In contrast to conventional multipixel cameras, single-pixel cameras capture images using a single detector that measures the correlations between the scene and a set of patterns. However, these systems typically exhibit low frame rates, because to fully sample a scene in this way requires at least the same number of correlation measurements as the number of pixels in the reconstructed image. To mitigate this, a range of compressive sensing techniques have been developed which use a priori knowledge to reconstruct images from an undersampled measurement set. Here, we take a different approach and adopt a strategy inspired by the foveated vision found in the animal kingdom—a framework that exploits the spatiotemporal redundancy of many dynamic scenes. In our system, a high-resolution foveal region tracks motion within the scene, yet unlike a simple zoom, every frame delivers new spatial information from across the entire field of view. This strategy rapidly records the detail of quickly changing features in the scene while simultaneously accumulating detail of more slowly evolving regions over several consecutive frames. This architecture provides video streams in which both the resolution and exposure time spatially vary and adapt dynamically in response to the evolution of the scene. The degree of local frame rate enhancement is scene-dependent, but here, we demonstrate a factor of 4, thereby helping to mitigate one of the main drawbacks of single-pixel imaging techniques. The methods described here complement existing compressive sensing approaches and may be applied to enhance computational imagers that rely on sequential correlation measurements.

https://advances.sciencemag.org/content/advances/3/4/e1601782.full.pdf

Adaptive foveated single-pixel imaging with dynamic supersampling

Single-pixel imaging uses a single-pixel detector, rather than a focal plane detector array, to image a scene. It provides advantages for applications such as multi-wavelength, three-dimensional imaging. However, low frame rates have been a major obstacle inhibiting the use of computational ghost imaging technique in wider applications since its invention one decade ago. To address this problem, a computational ghost imaging scheme, which utilizes an LED-based, high-speed illumination module is presented in this work. At 32 × 32 pixel resolution, the proof-of-principle system achieved continuous imaging with 1000 fps frame rate, approximately two orders larger than those of other existing ghost imaging systems. The proposed scheme provides a cost-effective and high-speed imaging technique for dynamic imaging applications.

1000 fps computational ghost imaging using LED-based structured illumination.

Single-pixel cameras provide a means to perform imaging at wavelengths where pixelated detector arrays are expensive or limited. The image is reconstructed from measurements of the correlation between the scene and a series of masks. Although there has been much research in the field in recent years, the fact that the signal-to-noise ratio (SNR) scales poorly with increasing resolution has been one of the main limitations prohibiting the uptake of such systems. Microscanning is a technique that provides a final higher resolution image by combining multiple images of a lower resolution. Each of these low resolution images is subject to a sub-pixel sized lateral displacement. In this work we apply a digital microscanning approach to an infrared single-pixel camera. Our approach requires no additional hardware, but is achieved simply by using a modified set of masks. Compared to the conventional Hadamard based single-pixel imaging scheme, our proposed framework improves the SNR of reconstructed images by ∼ 50 % for the same acquisition time. In addition, this strategy also provides access to a stream of low-resolution ‘preview’ images throughout each high-resolution acquisition.

Ming-Jie Sun

Papers

Single-pixel three-dimensional imaging with time-based depth resolution

A Russian Dolls ordering of the Hadamard basis for compressive single-pixel imaging.

Adaptive foveated single-pixel imaging with dynamic supersampling

1000 fps computational ghost imaging using LED-based structured illumination.

Improving the signal-to-noise ratio of single-pixel imaging using digital microscanning